INDEX

Explanations

references to physical locations or positions, specifically focusing on the ground

oai_token-act-pair · gpt-3.5-turbo

references to the term "ground."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ansen

-0.83

 Sins

-0.73

 caut

-0.73

entric

-0.71

å£«

-0.69

aned

-0.68

uked

-0.67

anos

-0.66

xit

-0.66

 Gleaming

-0.62

POSITIVE LOGITS

floor

0.95

 floor

0.94

hog

0.91

sheet

0.82

 footing

0.79

side

0.79

raid

0.78

plane

0.77

 Floor

0.77

sheets

0.76

Activations Density 0.013%

references to physical locations or positions, specifically focusing on the ground

references to the term "ground."

No Comments

No Known Activations